Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that include various forms of the verb "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "is" followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    is checking state or type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeHead
    -0.54
     giro
    -0.53
     rapporti
    -0.50
    下载附件
    -0.49
     gentes
    -0.49
     jika
    -0.47
     cât
    -0.46
     if
    -0.46
     quanh
    -0.46
     wenn
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.73
    CppMethod
    0.67
    رشف
    0.65
     <=",
    0.65
     yours
    0.62
     valid
    0.61
     للاسماء
    0.60
    valid
    0.58
     alive
    0.58
    routeProvider
    0.57
    Act Density 0.154%

    No Known Activations